Interactive doll system

Abstract

To provide an interactive doll system with improved variation of reaction of a doll.SOLUTION: An interactive doll system 10 has: a doll body 100 which has a drive mechanism 180 for driving a mouth 101, a microphone 131, a speaker 121, a controlling part 110, and a communication part 130; and a server device 200 which includes an interactive AI engine 201. The controlling part 110 has: a transmission part 111 which generates first data based on a voice input from the microphone 131 and transmits the first data to the server device 200 via the communication part 130; a reception part which acquires from the server device 200 via the communication part 130 second data as output data output from the interactive AI engine 201 as a reply to the first data and causes the speaker 121 to output a sound based on the second data; and a drive mechanism control part 113 which controls the drive mechanism 180 based on the second data.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an interactive doll system. [Background technology]

[0002] Conventionally, dolls including stuffed toys and figures that can communicate have been provided. For example, Patent Document 1 provides a welfare stuffed toy that has a memory unit that records voice data, a voice output unit, a sensor unit that detects a predetermined motion of the doll, and a voice acquisition unit that acquires external voice. The memory unit stores voice data. This welfare stuffed toy can respond differently depending on whether it is placed on a desk or the like and spoken to, or whether it is spoken to while being held in one's arms, by using the sensor unit that detects the motion. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Utility Model Registration No. 3225956 Summary of the Invention [Problem to be solved by the invention]

[0004] The recorded data stored in the memory section of the doll's body is selected according to a predetermined condition. Therefore, the doll's responses tend to be formulaic, and the user may become bored with them. Therefore, a wide variety of responses is required for the doll in conversation.

[0005] An object of the present invention is to provide an interactive doll system with improved response variation. [Means for solving the problem]

[0006] The interactive doll system of the present invention comprises a doll body having a mouth, a drive mechanism for driving the mouth, a microphone, a speaker, a control unit, and a communication unit, and a server device including an interactive AI engine, the control unit having a transmitting unit that generates first data based on voice input from the microphone and transmits the first data to the server device via the communication unit, a receiving unit that acquires second data generated by the server device based on output data output by the interactive AI engine in response to the first data from the server device via the communication unit and causes the speaker to emit sound based on the second data, and a drive mechanism control unit that controls the drive mechanism based on the second data. Effect of the Invention

[0007] According to the present invention, it is possible to provide an interactive doll system with improved response variation. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a block diagram showing an interactive doll system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a front view showing the doll body of the interactive doll system according to the embodiment of the present invention. [Diagram 3] FIG. 2 is a flow diagram illustrating the operation of the interactive doll system according to an embodiment of the present invention. [Figure 4] FIG. 13 is a block diagram showing an interactive doll system according to a modified embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] An embodiment of the present invention will be described with reference to the drawings. As shown in Fig. 1, an interactive doll system 10 has a doll body 100 and a server device 200. The doll body 100 and the server device 200 are connected via the Internet.

[0010] As shown in FIG. 2, the doll body 100 is formed as a stuffed toy that resembles a bear and includes at least a mouth 101. The doll body 100 is provided with a drive mechanism 180 that operates the mouth 101. The drive mechanism 180 includes a sound sensor 181 and a motor 182, and can drive the mouth 101 to open and close. A microphone 131 is installed in the forehead of the doll body 100. A speaker 121 is installed in the vicinity of the mouth 101 of the doll body 100. A sound sensor 181 of the drive mechanism 180 is installed in the doll body 100 near the speaker 121. In addition, the doll body 100 is equipped with a CPU related to the control unit 110, a communication unit 130, a circuit board on which electronic components related to the memory unit 120 are mounted, a power source (battery box), and the like, which are described later.

[0011] Returning to Fig. 1, the doll body 100 has a drive mechanism 180 for driving the mouth 101, a speaker 121, a microphone 131, a sound sensor 181, a control unit 110, a storage unit 120, and a communication unit 130. The control unit 110 is composed of at least one processor, a CPU (Central Processing Unit), and is connected to the storage unit 120, the communication unit 130, the drive mechanism 180, the speaker 121, and the microphone 131. The control unit 110 reads out a control program stored in the storage unit 120 and executes various processes.

[0012] The storage unit 120 is configured with, for example, at least one memory such as a flash memory, an EEPROM (Electrically Erasable Programmable ROM), an SSD (Solid State Drive), or other storage device. In addition to the control program, the storage unit 120 stores voice data collected by a microphone 131 and various data.

[0013] The communication unit 130 is, for example, a network interface controller (NIC), and is connected to the server device 200 via the Internet 300, and is capable of transmitting and receiving various types of data.

[0014] The server device 200 includes a dialogue AI engine 201 and a voice recognition unit 202. Specifically, the dialogue AI engine 201 can use generative AI such as ChatGPT or Bing AI. In this embodiment, when text data of the contents of a question or the like is input, the dialogue AI engine 201 outputs (answers) text data corresponding to the input (contents).

[0015] The voice recognition unit 202 can convert input voice data into text data and output it.

[0016] The transmission unit 111, the reception unit 112, the drive mechanism control unit 113, and the voice synthesis unit 114 of the control unit 110 are functional units that function as a result of a control program stored in the storage unit 120 being executed.

[0017] The transmission unit 111 generates first data based on the voice input from the microphone 131. In this embodiment, the first data is voice data. The generated first data, which is the voice data, is stored in the storage unit 120. The transmission unit 111 transmits the voice data stored in the storage unit 120 to the server device 200 via the communication unit 130.

[0018] The receiving unit 112 acquires second data generated by the server device 200 based on output data output by the interactive AI engine 201 as a response to the first data from the server device 200 via the communication unit 130, and causes the speaker 121 to emit sound based on the acquired second data.

[0019] In this embodiment, the receiving unit 112 includes a voice synthesis unit 114 that converts text data into voice data. In this embodiment, the second data is text data. The receiving unit 112 converts the acquired second data, which is text data, into voice data by the voice synthesis unit 114, and causes the speaker 121 to emit the voice data.

[0020] The drive mechanism control unit 113 controls the drive mechanism 180 according to a detection value of the sound sensor 181. The sound sensor 181 can detect the intensity of the sound emitted from the speaker 121. In this embodiment, the drive mechanism control unit 113 detects the sound based on the second data emitted from the speaker 121 by the sound sensor 181, and controls the drive mechanism 180 based on the detection value of the sound sensor 181.

[0021] For example, when the sound sensor 181 detects a sound with a sound pressure (or wavelength) greater than a predetermined threshold for identifying a strong sound, it can control the drive mechanism 180 to open the mouth 101 wider, and conversely, when it detects a small sound pressure (or wavelength), it can control the drive mechanism 180 to open the mouth 101 less. In other words, the drive mechanism control unit 113 controls the drive mechanism 180 based on the second data.

[0022] The process flow of the interactive doll system 10 will be described with reference to FIG. Step S10: The power supply of the doll body 100 is turned on to start processing. When the user speaks to the doll body 100, the spoken voice is recorded. Specifically, the transmission unit 111 generates first data, which is voice data, from the voice input from the microphone 131 and stores it in the storage unit 120. The transmission unit 111 can start generating voice data (first data) when voice is input from the microphone 131, and can end generating voice data (first data) when a silent state continues for a predetermined time.

[0023] Step S20: When the generation of the first data is completed, the transmission unit 111 transmits the voice data (first data) as the recorded voice stored in the storage unit 120 to the server device 200 via the communication unit .

[0024] Step S30: The server device 200 receives the first data and converts the first data, which is converted into voice data by the voice recognition unit 202, into text data. Then, the server device 200 inputs the converted text data into the dialogue-type AI engine 201.

[0025] Step S40: The interactive AI engine 201, to which text data based on the first data has been input, outputs a response to the input first data as text data. In this manner, the server device 200 generates second data based on the output data (text data) output by the interactive AI engine 201 as a response to the first data. In this embodiment, the text data output by the interactive AI engine 201 is used as the second data as is.

[0026] Step S50: The server device 200 transmits the text data (second data) output by the dialogue type AI engine 201 to the doll body 100. Step S60: The receiving unit 112 acquires the text data (second data) from the server device 200 via the communication unit .

[0027] Step S70: The receiving unit 112 converts the acquired text data (second data) into voice data by the voice synthesis unit 114. Step S80: The receiving unit 112 emits voice data based on the acquired text data (second data) from the speaker 121. That is, a response to what the user said is emitted from the doll body 100.

[0028] Step S90: The drive mechanism control section 113 operates the drive mechanism 180 in response to the detection of the sound sensor 181 to drive the mouth section 101. That is, the mouth section 101 opens and closes in response to the sound emitted from the speaker 121, so that the user can feel as if the doll body 100 is speaking.

[0029] Although the embodiment of the present invention has been described above, the present invention is not limited to the embodiment, and can be embodied in various forms. For example, as shown in a modified example of the embodiment of the present invention in FIG. 4, the server device 200 can be configured by a first server device 210 and a second server device 220. The first server device 210 includes a dialogue-type AI engine 201 and a voice recognition unit 202. The second server device 220 includes a voice synthesis unit 203.

[0030] That is, in the modified example of Fig. 4, the speech synthesis unit 114 included in the receiving unit 112 in the embodiment of Fig. 1 is removed from the receiving unit 112, and a second server device 220 is provided with a speech synthesis unit 203 having the same function as the speech synthesis unit 114 in the embodiment of Fig. 1. The first server device 210 converts the first data, which is voice data, into text data by a speech recognition unit 202 and inputs the text data to an interactive AI engine 201.

[0031] Then, the first server device 210 transmits output data (text data) output (response) by the interactive AI engine 201 to the input text data to the second server device 220. The second server device 220 converts the text data output by the interactive AI engine into voice data by the voice synthesis unit 203. In this manner, in this modification, the second server device 220 of the server device 200 generates the second data as voice data.

[0032] 4, the doll body 100 can obtain the second data, which is voice data, through the receiving unit 112 and the communication unit 130, and can emit sound from the speaker 121 without converting the data. Therefore, the structure of the doll body 100 can be simplified.

[0033] In addition, for example, the drive mechanism control unit 113 can obtain sound data from the receiving unit 112, determine the intensity of the sound from the sound data, and control the drive mechanism 180. This makes it possible to omit a sound sensor. [Explanation of symbols]

[0034] 10 Interactive doll system 100 Doll body 101 Mouth part 110 Control part 111 transmitting unit 112 receiving unit 113 Drive mechanism control unit 114 Voice synthesis unit 120 Memory unit 121 Speaker 130 Communications Department 131 Microphone 180 Drive mechanism 181 Sound sensor 182 Motor 200 Server device 201 Conversational AI engine 202 Speech recognition unit 203 Voice synthesis unit 210 First server device 220 Second server device 300 Internet

Claims

1. a doll body having a mouth, a drive mechanism for driving the mouth, a microphone, a speaker, a control unit, and a communication unit; A server device including an interactive AI engine; having The control unit is a transmission unit that generates first data based on the voice input from the microphone and transmits the first data to the server device via the communication unit; a receiving unit that acquires second data generated by the server device based on output data output by the interactive AI engine as a response to the first data from the server device via the communication unit and causes the speaker to emit sound based on the second data; a drive mechanism control unit that controls the drive mechanism based on the second data; An interactive doll system having:

2. The drive mechanism includes a motor.

2. The interactive doll system according to claim 1, wherein the drive mechanism control unit includes a sound sensor for detecting the intensity of the sound emitted from the speaker.

3. The server device includes a first server device including the interactive AI engine and a voice recognition unit, and a second server device including a voice synthesis unit, The first server device converts the first data, which is voice data, into text data using the voice recognition unit and inputs the text data to the interactive AI engine, and transmits text data output by the interactive AI engine in response to the input to the second server device; The second server device converts the text data output by the interactive AI engine into voice data by the voice synthesis unit to generate the second data.

3. An interactive doll system according to claim 1 or 2.

Images